Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to supplementary or additional components and their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    something is not primary

    np_acts-logits-general · gemini-2.0-flash

    supplementary, secondary, auxiliary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.63
    GenerationType
    -0.58
    Abit
    -0.56
     Italijani
    -0.55
    المشاركات
    -0.51
    vels
    -0.50
     ویکی‌پدی
    -0.49
     PyLong
    -0.49
     DETERMIN
    -0.48
    Merkmale
    -0.48
    POSITIVE LOGITS
     accessory
    0.57
     auxiliary
    0.56
     corollary
    0.53
    cillary
    0.52
     secundarios
    0.50
     secondary
    0.49
    Secondary
    0.48
     supplement
    0.48
     supplementary
    0.47
     Accessory
    0.46
    Act Density 1.071%

    No Known Activations